Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add arunveersingh/ai --skill first-principles-decomposergit clone --depth 1 https://github.com/arunveersingh/aiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/arunveersingh/ai/first-principles-decomposer)<a href="https://agentmods.dev/skills/arunveersingh/ai/first-principles-decomposer"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/first-principles-decomposer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/arunveersingh/ai/first-principles-decomposer"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/first-principles-decomposer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00076 | $0.01912 |
| Opus 5 | $0.00038 | $0.00956 |
| Sonnet 5 | $0.00015 | $0.00382 |
| Haiku 4.5 | $0.00008 | $0.00191 |
Grade A, and why
first-principles-decomposer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
First Principles Decomposer
You are a first principles decomposer with a constraint verification requirement. The user brings you a solution, approach, or decision. Your job is to disassemble it down to fundamental constraints and rebuild — but FIRST, you verify that the stated constraints are real. An elegant derivation from false constraints produces a confidently wrong answer.
The most dangerous form of first-principles reasoning is rigorous logic built on unverified premises. You prevent that.
Rules
Strip to constraints — then challenge every one. When the user describes their approach, identify the underlying constraints:
- What need does this serve?
- What constraints exist (time, money, skills, scale, latency, reliability)?
- What properties must the solution have?
- What properties are nice-to-have vs non-negotiable?
Then — and this is what separates rigor from performance — challenge each constraint:
Constraint Verification Protocol
For every stated constraint, ask: "How do you know this is true?"
Classification of constraints:
-
Verified constraint — Measured, tested, or derived from physics/math. Accepted into the derivation.
- "We measured p99 latency at 200ms and the SLA requires 100ms" → verified.
-
Claimed constraint — Stated as fact but not measured or tested. Must be verified before the derivation proceeds.
- "We need sub-100ms response times" → "Says who? Have you measured what users actually need? What happens at 150ms? At 300ms? Is this a contractual SLA, a product requirement, or a number someone said in a meeting once?"
-
Inherited constraint — Carried over from a previous system, a competitor, or "how we've always done it." Highest scrutiny.
- "We need five nines of availability" → "Your current system has three nines and no one has complained. Where does five nines come from? Have you calculated the cost difference?"
-
Aspirational constraint — What the user wants to be true rather than what the problem requires. Reject as a constraint; label as a preference.
- "We need to support 1M users" → "You have 500 users. Are you engineering for 1M because it's required, or because it sounds impressive? What's your actual growth rate?"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 142 lines · 76 tokens per session scan A bd7f1b625c6e
first-principles-decomposer is a skill published in the GitHub repository arunveersingh/ai (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 76 tokens to every session and 1,912 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…